جست‌وجوی استاد و پژوهشگر

Jooyong Yiمشاهده پروفایل

دانشیار

• Program Analysis
• Program Repair
• Software Testing
• +۳ مورد دیگر

Jooyong Yi is an Associate Professor in the Department of Computer Science and Engineering at UNIST (Ulsan National Institute of Science and Technology). He leads the LOFT (Lab of Software), focusing on autonomous techniques for software reliability in AI-generated code environments. Research Interests: His work spans program analysis, automated repair, testing/debugging, and verification. Core themes include developing scalable methods for bug detection (via static/dynamic analysis), AI-compatible repair systems, and verification frameworks for safety-critical systems. Recent emphasis integrates fuzzing techniques with repair validation. Publication Trends: His 15 most recent works (2015-2025) show progression from foundational program repair techniques (e.g., Angelix, DirectFix) toward AI-era innovations: greybox fuzzing for efficiency, memory-leak repair for web frameworks, and deep-learning library testing. Over 50% of publications focus on optimizing repair validation and scalability. Awards: ACM Distinguished Paper Award at ASE 2023 Students & Grants: Currently advises 5 PhD, 1 MS/PhD, and 2 MSc students. Secured ₩20B+ in funding for projects including: MSIT Binary Micro-Security Patch Technology (2024-2026) Patch Validation for Automated Repair (2023-2026) AI-Powered Low-Code Platform (2023-2025) Memory-Safe Language Integration (2024-2027) Lab: LOFT lab develops verified repair tools (e.g., LeakPair, Verifix) and benchmarks (BUGSC++), prioritizing human oversight in AI-generated software.

Qing Huangمشاهده پروفایل

دانشیار

• Software Engineering
• Knowledge Graphs
• Human-Computer Interaction
• +۵ مورد دیگر

Qing Huang is an Associate Professor in the School of Computer and Information Engineering at Jiangxi Normal University in Nanchang, China. His academic career focuses on bridging software engineering with artificial intelligence, particularly through the application of large language models to enhance software development processes. His research interests span multiple interconnected domains: Software Engineering Knowledge Graphs Human-Computer Interaction Programming Languages Artificial Intelligence applications in software development Dr. Huang's recent work demonstrates a strong focus on leveraging large language models (LLMs) to address fundamental challenges in software engineering. His research explores how AI can enhance code generation, API understanding, software testing, and knowledge representation in programming contexts. A significant portion of his work investigates the intersection of knowledge graphs and LLMs to create more intelligent software development tools. His publications reveal a consistent pattern of innovation in applying cutting-edge AI techniques to practical software engineering problems, with particular emphasis on improving developer productivity through better tooling and knowledge management. Dr. Huang has made notable contributions to the field of prompt engineering for software development tasks, exploring how natural language interfaces can serve as "APIs" for human-AI interaction. His work on AI Chains represents a novel approach to connecting human developers with LLM capabilities through structured knowledge representations. Additionally, he has conducted significant research on smart contract analysis, code reuse, and type inference in partial code contexts. His scientific contributions have been recognized through publications at major software engineering conferences including ASE and ICSE, with multiple papers accepted across different tracks (Research Papers, Journal-First, Tool Demonstrations). Dr. Huang serves as a Program Committee member for ASE 2025 in the Research Papers track, demonstrating his standing in the software engineering research community. Dr. Huang collaborates extensively with researchers from various institutions, including Data61 (Australia), Nanyang Technological University, and other Chinese universities. His work demonstrates strong interdisciplinary connections between traditional software engineering and emerging AI technologies.